Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/callmetechie/fleet-manager/compose-listgit clone --depth 1 https://github.com/CallMeTechie/fleet-managerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.00315 |
| Opus 5 | $0.00010 | $0.00158 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
compose-list scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Compose List
set -euo pipefail
source "${CLAUDE_PLUGIN_ROOT:-plugin}/commands/_compose-lib.sh"
NAME="$(resolve_server "$(printf '%s' "$ARGUMENTS" | tr -d '[:space:]')")"
build_ssh "$NAME"; echo_target "$NAME"
resolve_docker_cmd "$NAME"; docker_precheck
RAW="$(compose_ls_json)"
COUNT="$(echo "$RAW" | jq 'length' 2>/dev/null || echo 0)"
if [ "$COUNT" = "0" ]; then echo "No compose projects on $NAME."; exit 0; fi
printf "%-22s %-16s %s\n" "PROJECT" "STATUS" "CONFIG"
# `|| true`: don't let a jq hiccup abort the command under pipefail after the header.
echo "$RAW" | jq -r '.[] | [.Name, .Status, .ConfigFiles] | @tsv' \
| while IFS=$'\t' read -r n s c; do printf "%-22s %-16s %s\n" "$n" "$s" "$c"; done || true
ACTIVE="$(echo "$RAW" | jq '[.[] | select(.Status | startswith("running"))] | length')"
echo ""; echo "Verdict: $ACTIVE running of $COUNT total"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 28 lines · 20 tokens per session scan A 85a3cbc6d9f1
compose-list is a command published in the GitHub repository CallMeTechie/fleet-manager (1 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 315 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
cleanup
Clean up TTS cache files to free up disk space.
deps-age
Analyze dependency freshness and maintenance activity.
release-prep
Automated release readiness validation.
review-pr
Comprehensive PR review checklist to ensure code quality, testing, and best practices.